Hacker News new | past | comments | ask | show | jobs | submit login
[flagged] Play Dialog: A contextual turn-taking TTS model like NotebookLM Playground (play.ai)
49 points by dulldata 83 days ago | hide | past | favorite | 13 comments



PlayAI (fma PlayHT) founder here, this is a native multiturn voice model that is built for conversations like real-time agents or podcasts. Try it through our playground (https://play.ai/playground) or API (https://docs.play.ai/). Feel free to ask anything.


Ouch. If you know Arabic or Hebrew, try selecting those languages and typing something in—it’s hilarious.

Looks like they’re “testing in production.”


The current deployed model is English only, we are rolling out a multilingual version later this week!


Oh. the UI lets you select fro various languages, so I assumed they should work. Thanks!


overall impressive. noticed a weird quirk of reading $100 million as "one hundred dollar million" instead of one hundred million dollars


Love the idea but this is not good yet. Mine had random changes in pace/cadence of speech and was basically uncanny valley territory


This is impressively low latency. Also, it's cool to see another option for TTS with real-time streaming.


if you are developer, then there's an api - https://docs.play.ai/tts-api-reference/endpoints/v1/tts/stre...


did you listen to the output of your own demo?

> Speaker 1: Dang man, I’d come find you for sure.

that part sounds like a broken robot


Hey, can you give an example ? The model is not perfect and this is our first version, so will get better and faster for sure. Still I generated the full prompt you referenced and it sounds good to me. Adds some laughter, but this makes it more non-robotic in my mind.

https://drive.google.com/file/d/1JzfweTdvCWzJ6Wwv0KdgfaxZcyn...

Speaker 1: Oh yes, the deep sea, nature’s basement. Home to creatures so bizarre, even nightmares are like, “Nah, I’ll pass.” Speaker 2: Right? It's like the ocean was running a clearance sale on leftover parts. “Hey, who wants a fish with a lightbulb head? No one? Alright, let’s just drop this bad boy in the Mariana Trench.” Speaker 1: Oh man, let’s start with a classic: the anglerfish. It’s a fish that decided it was uh, tired of chasing its food and thought, “What if I just dangle a glow stick on my head and let dinner come to me?” Speaker 2: Honestly, I respect that. Can you imagine if we had that? Like, I’m sitting on my couch with a glowing Dorito on my forehead, waiting for snacks to find me. Speaker 1: Dang man, I’d come find you for sure.


i don't think anyone has done real-time multi-speaker dialog generation before


[flagged]


Fake account / bot meant to promote the company. Look at comment history.


Please email hn@ycombinator.com to report these kinds of things.




Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: